ralph
Self-referential loop until task completion with configurable verification reviewer
Best for Mission-critical developmen…Works with GitHub
⌘source
- author
@Yeachan-Heo- language
- TypeScript
★30kstars
2.8kforks
Apr 18, 2026
✦overview.md
Key Features
- ·Persistent execution loop until all PRD user stories pass
- ·Automatic retry on failure with session persistence
- ·Mandatory reviewer verification before task completion
- ·Structured story tracking via prd.json
- ·Configurable critic reviewer (architect, critic, codex)
Use Cases
- →Guaranteeing completion of complex tasks with verification requirements
- →Implementing PRD-driven development with mandatory sign-off
- →Handling work that spans multiple iterations needing persistence
- →Automating tasks where partial implementations are unacceptable
Best for
- ✓Mission-critical development tasks
- ✓PRD-driven workflows
- ✓Quality-sensitive automation
Not ideal for
- !Quick one-shot fixes
- !Exploratory planning phases
- !Manual control scenarios
- !Full autonomous pipelines
FAQs
name
ralph
description
Self-referential loop until task completion with configurable verification reviewer
argument-hint:[--no-deslop] [--critic=architect|critic|codex] <task description>
level:4
[RALPH + ULTRAWORK - ITERATION {{ITERATION}}/{{MAX}}]
Your previous attempt did not output the completion promise. Continue working on the task.
<Purpose> Ralph is a PRD-driven persistence loop that keeps working on a task until ALL user stories in prd.json have passes: true and are reviewer-verified. It wraps ultrawork's parallel execution with session persistence, automatic retry on failure, structured story tracking, and mandatory verification before completion. </Purpose><Use_When>
- Task requires guaranteed completion with verification (not just "do your best")
- User says "ralph", "don't stop", "must complete", "finish this", or "keep going until done"
- Work may span multiple iterations and needs persistence across retries
- Task benefits from structured PRD-driven execution with reviewer sign-off </Use_When>
<Do_Not_Use_When>
- User wants a full autonomous pipeline from idea to code -- use
autopilotinstead - User wants to explore or plan before committing -- use
planskill instead - User wants a quick one-shot fix -- delegate directly to an executor agent
- User wants manual control over completion -- use
ultraworkdirectly </Do_Not_Use_When>
$install
1-click copynpx skills add Yeachan-Heo/oh-my-claudecode --skill ralphSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
3/ 5
goodMostly clear, but there are still a few confusing or poorly structured parts.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.